Question 1

What does the GPT-4o API cost?

Accepted Answer

The official OpenAI list price is $2.50 per 1M input tokens and $10 per 1M output tokens. Cached input is $1.25 per 1M tokens, 2× cheaper than the regular input.

Question 2

How much does 1 million tokens of GPT-4o cost?

Accepted Answer

1M input tokens cost $2.50, 1M output tokens — $10. With a 1:1 input/output load a million tokens works out to about $6.25. Chatbots with long context push the blended price down; code generation pushes it up.

Question 3

Where is the GPT-4o API cheapest?

Accepted Answer

Our measurements show RunAPI as the cheapest: 94% below the official price. Quotes from 3 providers refresh daily — see the table above.

Question 4

What is the GPT-4o context window?

Accepted Answer

The context window is 200K tokens. Some vendors raise the price above a context threshold — check the plan notes.

Question 5

How do I check that a provider key works?

Accepted Answer

The free checker sends a GET request to your endpoint's model list and reports status and latency. The key is not stored server-side.

#	Provider	1M input	1M output	Discount	Tokens per $100
—	Official list	$2.50	$10.00	0%	26.7M
1	RunAPI	$0.150	$0.600	−94%	444M
2	Crazyrouter	$0.375	$1.50	−85%	178M
3	Polza.ai	$3.67	$14.69	—	18.2M

Cheapest GPT-4o API: RunAPI is 94% below the official price

What to check before buying